Browse Items (2150 total)
Sort by:
-
Detection of Lung Cancer with a Deep Learning Hybrid Classifier
This article presents a deep learning framework combining a convolutional neural network (CNN) and a support vector machine (SVM) for lung cancer diagnosis. The model uses data divided into six groups: 250 images in the training set and 150 images in the test set. The work includes preliminary data and development using the Keras image data generator, VGG-16 architecture, high-level rules, and SVM classifier training with labels and vectors. The model achieves 90% accuracy with 85% selection impact and 75% cross-validation flexibility using VGG-16 and SVM hybrid classifier. This study finally revealed the classification of the model by multi-class ROC curve analysis and confusion matrix. 2024 IEEE. -
A Dynamic Anomaly Detection Approach for Fault Detection on Fire Alarm System Based on Fuzzy-PSO-CNN Approach
Early detection is crucial due to the catastrophic threats to life and property that are involved with fires. Sensory systems used in fire alarms are prone to false alerts and breakdowns, endangering lives and property. Therefore, it is essential to check the functionality of smoke detectors often. Traditional plans for such systems have included periodic maintenance; however, because they don't account for the condition of the fire alarm sensors, they are sometimes carried out not when necessary but rather on a predefined conservative timeframe. They describe a data-driven online anomaly detection of smoke detectors, which analyzes the behavior of these devices over time and looks for aberrant patterns that may imply a failure, to aid in the development of a predictive maintenance approach. The suggested procedure begins with three steps: preprocessing, segmentation, and model training. A pre-processing unit can enhance data quality by compensating for sensor drifts, sample-to-sample volatility, and disturbances (noise). The proposed approach normalizes the data in preparation. The smoke source can be detected by using segmentation to differentiate it from the background. Following segmentation, Fuzzy-PSO-CNN is used to train the models. CNN and PSO, two of the most used alternatives, are both outperformed by the proposed method. 2023 IEEE. -
Python Driven Keyword Analysis for SEO Optimization
Every word or string of words a user types into a search engine has meaning. For example, a user might search for a 'hotel' or a 'hotel in New York City.' Keywords are the standard focus of search engine optimization (SEO), which offers a useful method of gauging demand for specific queries and aiding in a better understanding of how users look for goods, services, businesses, and, eventually, solutions. Any effective SEO strategy must include keyword research, and Python is a strong language that can be used to automate and accelerate the process. This project presents a Python-based keyword research tool that works on real-time data to identify the top searches over a user-specified domain to identify trends and customer needs. It does this by utilizing multiple Python libraries and Google Autocomplete. The Google Autocomplete results for the user-specified domain are first parsed by the tool before it can function. After that, unnecessary keywords are eliminated by filtering and cleaning the results. Subsequently, the remaining keywords are arranged for search volume and domain relevancy. The tool looks for trends by comparing the current keyword rankings with previous data. Thanks to this, users can see which keywords are growing in popularity. By identifying the most commonly asked questions and issues, the tool also offers insights into the needs of its users. The tool is simple and adaptable to each user's unique requirements. It can be used to create keyword lists for content marketing, SEO, and product development, among other uses. 2024 IEEE. -
Economic and Urban Dynamics: Investigating Socioeconomic Status and Urban Density as Moderators of Mobile Wallet Adoption in Smart Cities
This research paper examines the complex correlation between socioeconomic factors, urban density, and the acceptance of mobile wallet technology in smart cities. The study investigates how socioeconomic status and urban density influence the adoption of mobile wallets. Smart cities have experienced a significant increase in the adoption of mobile payment solutions such as Apple Pay, and Google Pay, noted for their technological innovation and ability to enhance living standards. These digital payment platforms provide ease, security, and efficiency, revolutionizing how individuals engage in financial transactions and navigate urban environments. The study examines the many aspects that impact this phenomenon, focusing on the significance of comprehending how socioeconomic status and urban density influence the acceptance of mobile wallets. The study utilizes a meticulous research technique, which involves evaluating the reliability and validity of constructs, analyzing Heterotrait-Monotrait (HTMT) ratios, conducting tests for discriminant validity, and doing variance inflation factor (VIF) analysis. These measures are taken to ensure the strength and reliability of the report's conclusions. The research's importance is further supported by model fit statistics and hypothesis testing conducted through bootstrapping. The results emphasize that the inclusion of mobile wallet functions, the legal framework, and the development of smart city infrastructure have a substantial influence on the acceptance of mobile wallets. However, the impact of urban density on mobile wallet adoption is more intricate and multifaceted. This study provides significant insights into the dynamic field of technology uptake in urban regions, with implications for politicians, entrepreneurs, and urban planners seeking to promote financial inclusion and technological integration in smart cities. 2024 IEEE. -
An Novel Cutting Edge ANN Machine Learning Algorithm for Sepsis Early Prediction and Diagnosis
Early detection and diagnosis of sepsis can significantly improve patient outcomes, but current diagnostic methods are limited. The problem addressed in this paper is the early detection and diagnosis of sepsis using machine learning algorithms. Sepsis is a life-threatening condition that can rapidly progress and cause organ failure, leading to increased mortality rates. Early detection and treatment of sepsis are critical for improving patient outcomes and reducing healthcare costs. However, sepsis can be challenging to diagnose, and existing methods have limitations in terms of accuracy and timeliness This research proposes a new cutting-edge Optimized Artificial Neural Network machine learning algorithm for sepsis early prediction and diagnosis. The proposed algorithm combines different data sources, including patient vital signs, laboratory results, and clinical notes, to predict the likelihood of sepsis development. The algorithm was evaluated on a large dataset of patient records and achieved promising results in terms of accuracy, Precision and Recall. The proposed algorithm can potentially serve as a valuable tool for clinicians in the early detection and diagnosis of sepsis, leading to better patient outcomes. 2023 American Institute of Physics Inc.. All rights reserved. -
AI-enabled risk identification and traffic prediction in vehicular Ad hoc Networks
The proposed research presents a two-fold approach for advancing Vehicular Ad-Hoc Networks (VANETs). Firstly, it introduces a Residual Convolutional Neural Network (RCNN) architecture to extract real-time traffic data features, enabling accurate traffic flow prediction and hazard identification. The RCNN model, trained and tested on real- world data, outperforms existing models in both accuracy and efficiency, promising improved road safety and traffic management within VANETs. Secondly, the study introduces a Genetic Algorithm-enhanced Convolutional Neural Network (GACNN) routing algorithm, challenging traditional VANET routing methods with metaheuristic techniques. Experiments in various VANET network scenarios confirm GACNN's superior performance over existing routing protocols, marking a significant step toward more efficient and adaptive VANET traffic management. 2024 Author(s). -
Mitigating post-harvest losses through IoT-based machine learning algorithms in smart farming
This research paper explores the transformative potential of Internet of Things (IoT) technology in mitigating the longstanding issue of post-harvest losses within the agriculture sector. These losses, which encompass both quantitative and qualitative deterioration of food commodities from harvest to consumption, have posed persistent challenges, resulting in economic losses and food wastage. By delving into the current landscape of post-harvest losses and the application of IoT technology, the paper offers valuable insights into how IoT can be harnessed to reduce these losses effectively. It not only highlights the benefits and existing IoT solutions but also addresses the inherent challenges, providing recommendations for their resolution. Moreover, the research introduces a machine learning-based model, specifically Random Forest ML, to identify and prevent losses in tandem with IoT devices, empowering farmers with timely alert messages for informed decision-making, thus fostering a more sustainable and efficient agricultural ecosystem. 2024 Author(s). -
Detecting Deepfake Voices Using a Novel Method for Authenticity Verification in Voice-Based Communication
The widespread use of deepfake technology in recent years has given rise to grave worries about the alteration of audio-visual material. The integrity of voice-based communication is particularly vulnerable to the threat posed by deepfake voice synthesis. The development of cutting-edge methods for the identification of deepfake voices is examined in this paper, which also offers a thorough analysis of current approaches, their advantages, and disadvantages. The research presents a novel method for detecting deepfakes in voice recordings that uses signal processing, machine learning, and audio analysis to separate synthetic voices from authentic voices. By achieving superior accuracy in differentiating between real and deepfake voices, and proposed method supplies a strong barrier against the misuse of voice synthesis technology for malicious purposes, also go over the research some of the possible uses for this technology, like voice authentication system security and social media platform content moderation. The paper's insights will support continued efforts to strengthen the authenticity of voice communication in the digital age and reduce the risks associated with deepfake voice synthesis. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Machine Learning Model Enabled with Data Optimisation for Prediction of Coronary Heart Disease
Cardiovascular disorders remain leading cause for mortality worldwide, necessitating robust early risk assessment. Although machine learning models show promise, most rely on conventional preprocessing, which lacks model portability across datasets. We propose an integrated preprocessing pipeline enhancing model generalizability. Our methodology standardises features solely based on training statistics and then transforms test data identically to prevent leakage. We handle class imbalance through synchronised oversampling, enabling consistent performance despite distribution shifts. This framework was evaluated on an open-source dataset of clinical parameters from an African cohort using classifiers like support vector machines and gradient boosting. All models achieved upto 80% accuracy. Remarkably, evaluating the identical models on five external European and Asian datasets maintains 80% - 86% accuracy. Our reproducible data conditioning strategy enables precise and transportable heart disease risk prediction, overcoming population variability. The framework provides the flexibility to readily retrain models on new data or update risk algorithms for clinical implementation in diverse locales. Our work accelerates the safe translation of machine learning to guide cardiovascular screening worldwide. 2024 IEEE. -
A Survey on Enhancing System Performance of Wireless Sensor Network by Secure Assemblage Based Data Delivery
To provide secure data transmission in Cluster Wireless Sensor Networks (CWSNs), the challenging task is to provide an efficient key management technique. To enhance the performance of sensor networks, clustering approach is used. Wireless Sensor Network (WSN) comprises of large collection of sensors having different hardware configurations and functionalities. Due to limited storage space and battery life, complex security algorithms cannot be used in sensor networks. To solve the orphan node problem and to enhance the performance of the WSN, authors introduced many secure protocols such as LEACH, Sec-LEACH, GS-LEACH and R-LEACH, which were not secure for data transmission. The energy consumption in existing approach is more due to overhead incurred in computation and communication in order to achieve security. This paper studies about different schemes used for secure data transmission. We are proposing new methodology called IBDS and EIBDS that will increase the performance of WSN by reducing computational overhead and also increases resilience against the adversaries. 2017 IEEE. -
Catalyzing Security and Efficiency: Blockchains Integration with IoT and Cloud Computing
Blockchain technology is a system that combines a number of computer technologies, encryption, shared storage, namely intelligent contracts, consensus processes, and peer-to-peer (P2P) networks. This research project begins with a description of the architecture of blockchains, followed by a comparison of the various consensus techniques used across various blockchain implementations. This studys scope includes a thorough analysis of the entire blockchain ecosystem. Our investigation also explores the complexity of the consensus models built into different blockchain platforms. This research painstakingly dissects these elements to pinpoint crucial elements that are essential for propelling the adoption and development of blockchain technology. In conclusion, our research corrects misconceptions about blockchains expansive potential and helps to direct the development of the technology across a wide range of industries. These results are significant for determining the future direction of blockchains enduring influence. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Relative Efficiencies of Farmer Producer Companies in India- Slack-Based Model Approach
The concept of the farmer producer company (FPC) model has received a large momentum especially during the 20202021 farmers' protest in India. This paper examines the relative efficiencies of 46 FPCs in Kerala using non-radial data envelopment analysis (DEA) for the financial year 2018-19. We use a non-oriented slack-based model (SBM) under assumptions of constant and variable returns to scale. The results reveal that 36.96 per cent of the sample FPCs are overall technical efficient and 50 per cent of the FPCs are pure technical efficient. It is found that technical inefficiency is reported for a few FPCs due to scale inefficiency. Among the input and output targets suggested for inefficient FPCs, reduction in the 'number of shareholders' and augmentation of 'profits' reported in most cases to improve their efficiency scores. Based on the findings, we suggest the concerned stakeholders to provide additional financial and non-financial supports to the needy rather than focusing on establishing new FPCs. 2022 IEEE. -
Depth Wise Separable Convolutional Neural Network with Context Axial Reverse Attention Based Sentiment Analysis on Movie Reviews
Sentiment Analysis (SA) in movie reviews involves using natural language processing techniques to determine the sentiment expressed in reviews. This analysis helps in understanding the overall audience sentiment towards a movie, categorizing reviews as positive, negative, or neutral. It's useful for filmmakers, marketers, and audiences. The existing methods does not provide sufficient accuracy, error rate and complexity was increased. To overcome the aforementioned problem, Depth Wise Separable Convolutional Neural Networks with Context Axial Reverse Attention Network (DWSCNN-CARAN) is proposed for accurately classifying SA in movie reviews. In this input image is taken from two datasets such as IMDB dataset and Polarity dataset. The pre-processing is done using six steps namely, Cleaning, Tokenization, Case Folding, Normalization, Stop Word Elimination, and Stemming for the purpose of removing noises. Following that feature extraction are done using Bag-Of-Words and Term Frequency-Inverse Document Frequency (BOW-TF-IDF). After that classification are done using Depth Wise Separable Convolutional Neural Networks with Context Axial Reverse Attention Network (DWSCNN-CARAN)for classifying the AS in movie reviews. The efficiency of the proposed DWSCNN-CARAN-BOA is analyzed using a dataset and attains 99.94% accuracy, 98.76% recall and attains better results compared with the existing methods. In the future, this approach will use the adversarial instances it generated to conduct adversarial training and assess the potential improvement in classification performance. It also looks into the possibilities of creating adversarial examples at the word and sentence levels by combining structured knowledge from high-quality knowledge bases. 2024 IEEE. -
Unsupervised Feature Selection Approach for Smartwatches
Traditional feature selection methods can be time-consuming and labor-intensive, especially with large datasets. This studys unsupervised feature selection approach can automate the process and help identify important features preferred by a particular segment of users. The unsupervised feature selection method is applied for smartwatches. Smartwatches continue to gain popularity. It is important to understand which features are most important to users to design and develop smartwatches that are more engaging, user-friendly, and meet the needs and preferences of their target audience. The rapid pace of technological innovation in the smartwatch industry means that new features and functionalities are constantly being developed. Multi-cluster feature selection, Laplacian score, and unsupervised spectral feature are used. Conjoint analysis is done on the most common features in all three selection methods. The unsupervised feature selection technique is used for identifying the relevant and important features of new smartwatch users.The practical implication of the research is in the application of the technique in the new product design of smartwatches. The result of the study also informs smartwatch manufacturers and developers on the features they need to prioritize and invest in. This can ultimately result in better and more user-friendly smartwatches and a good overall experience for the user. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Predictive Modelling of Factors Influencing Job Satisfaction Through a CNN-BiGRU Algorithm
The fields of humanities, psychology, and sociology are where the word 'job satisfaction' originated. According to psychology, it is a condition in which a worker experiences his circumstances emotionally and responds by experiencing either pleasure or suffering. It is regarded as a variable in various sociological categories pertaining to how each employee assesses and thinks about his work. Because a satisfied employee contributes to and builds upon an organization's success, job satisfaction is intimately tied to an employee's performance and the quality of the work they do. As a result, job satisfaction directly correlates to an organization's success. The proposed strategy incorporates data preprocessing, feature selection, and model training. The missing value is a common feature of data preparation. Feature selection is chosen using the ANOVA F-Test Filter, the Chi-Square Filter, and the full Data Set Construction procedure. The model's efficacy can be evaluated with the help of CNN-BiGRU. The proposed technique is compared to two more models: BiGRU and CNN. It has been shown that our proposed technique outperforms two other models. 2023 IEEE. -
Predicting Price Direction of Bitcoin based on Hybrid Model of LSTM and Dense Neural Network Approach
Bitcoin is a rapidly growing but extremely risky cryptocurrency. It marks a watershed moment in the history of cash. These days, digital currency is preferred to actual money. Bitcoin has decentralized authority and placed it in the hands of its users. Many people are joining the largest and most well-known Bitcoin mining pools as the risk of working alone is too great. In order to enhance their chances of creating the next block in the Bitcoins blockchain and decrease the mining reward volatility, users can band together to form Bitcoin pools. This tendency toward consolidation may also be seen in the rise of large-scale mining farms equipped with powerful mining resources and speedy processing capability. Because of the risk of a 51% assault, this pattern shows that Bitcoin's pure, decentralized protocol is moving toward greater centralization in its distribution network. Not to be overlooked is the resulting centralization of the bitcoin network as a result of cloud wallets making it simple for new users to join. Because of the easily hackable nature of Bitcoin technologies, this could lead to a wide range of security vulnerabilities. The proposed approach uses normalization and filling missing values in preprocessing, PCA for feature Extraction and finally training the model using LSTM-DNN Models. The proposed approach outperforms other two models such as CNN and DNN. 2023 IEEE. -
Handwritten Telugu Character Recognition Using Machine Learning
The Telugu language is the most prominent representative within the Dravidian language family, predominantly spoken in the southeastern regions of India. Handwritten character recognition in Telugu has significant applications across diverse fields such as healthcare, administration, education, and paleography. Despite its importance, the Telugu script differs significantly from English, presenting distinct challenges in recognizing characters due to its complexity and diverse character shapes. This study explores the application of machine learning, particularly delving into deep learning techniques, to improve the accuracy of Telugu character recognition. This paper proposes a model to recognize handwritten Telugu characters using Convolutional Neural Network (CNN). The proposed study demonstrates the accuracy in identifying diverse handwritten Telugu characters. We assess the system's performance against conventional and machine learning methodologies and preprocess an extensive dataset to guarantee strong model training. The proposed model excels in accurately predicting visually similar but distinct characters, achieving an impressive accuracy rate of 96.96%. 2024 IEEE. -
Enhanced Automated Oxygen Level controller for COVID Patient By Using Internet of Things (IoT)
The Internet of Things (IoT) shall be merged firmly and interact with a higher number of altered embedded sensor networks. It provides open access for the subsets of information for humankind's future aspects and on-going pandemic situations. It has changed the way of living wirelessly, with high involvement and COVID-related issues that COVID patients are facing. There is much research going on in the recent domain, like the Internet of Things. Considering the financial-economic growth, there isn't much significance as IoT is growing with industry 5.0 as the latest version. The newly spreading COVID-19 (Coronavirus Disease, 2019) will emphasize the IoT based technologies in a greater impact. It is growing with an increase in productivity. In collaboration with Cloud computing, it shows wireless communication efficiently and makes the COVID-19 eradication in a greater way. The COVID-19 issues which are faced by the COVID patients. Many patients are suffering from inhalation because of lung problems. The second wave attacks mainly on the lungs, where there is a shortage of breathing problems because of less supply of oxygen (insufficient amount of oxygen). The challenges emphasized as proposed are like the shortage of monitoring the on-going process. Readily being active in this pandemic situation, the mentioned areas are from which need to be discussed. The frameworks and services are given the correct data and information for supply of oxygen to the COVID patients to an extent. The Internet of Things also analyzes the data from the user perspective, which will later be executed for making on-demand technology more reliable. The outcome for the COVID-19 has been taken completely to help the on-going COVID patients live, which can be monitored through Oxygen Concentration based on the IoT framework. Finally, this article discusses and mentions all the parameters for COVID patients with complete information based on IoT. 2022 IEEE. -
Cloud Computing Application: Research Challenges and Opportunity
In a world with intensive computational services and require optimal solutions, cloud security is a critical concern. As a known fact, the cloud is a diverse field in which data is crucial, and as a result, it invites the dark world to enter and create a virtual menace to businesses, governments, and technology that is facilitated by the cloud. This article addresses the fundamentals of cloud computing, as well as security and threats in various applications. This research study will explore how security is remaining as a potential risk for cloud users across the globe by listing some of the cloud applications. Some viable solutions and security measures that could help us in analyzing cloud security threats are reviewed. The analyzed solutions include profound analytical thinking on how to render the solutions more impactful in each scenario. Several cloud security solutions are available to assist businesses in reducing costs and enhancing security. This study discover that if the risks are taken into consideration without any delay then the matter of solutions gets divided into four pillars, which will assist us in obtaining a more comprehensive knowledge. Visibility, compute-based security, network protection, and lastly identity security are referred as four pillars. 2022 IEEE. -
Diabetes Mellitus Classification Using Machine Learning Algorithms with Hyperparameter Tuning
Diabetes Mellitus is a prevalent condition globally, marked by elevated blood sugar levels resulting from either insufficient production of insulin or the body cells' inability to respond appropriately to released insulin. For people with diabetes to lead healthy, normal lives, early identification and treatment of the condition are essential. With the need to move away from current traditional procedures, towards a noninvasive methodology, machine learning and data mining technologies can be very useful in the classification of diabetes. Creating an effective machine learning model for the classification of diabetes mellitus was the primary goal of this research. This work is primarily carried out on combined Pima Indian diabetes dataset and German Frankfurt diabetes dataset. The class imbalance issue has been resolved using Synthetic Minority Oversampling Technique. One-hot encoding is applied to convert categorial features to numerical and various single and ensemble classifiers with the best hyperparameters obtained using GridSearchCV method were employed on the pre-processed dataset. With an AUC of 0.98 and maximum accuracy of 98.79%, the Random Forest ensemble technique outperformed the other models, according to the experimental results. As a result, the algorithm might be used to predict diabetes and alert doctors to serious cases that call for emergency care. 2024 IEEE.